github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14068] CUDA error with qwen3-coder-next on Windows when using 0.15.5-rc2 #34950

New Issue
Closed
opened 2026-04-22 18:59:37 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 18:59:37 -05:00
Owner
Copy Link

Originally created by @rskupnik on GitHub (Feb 4, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14068

Originally assigned to: @jmorganca on GitHub.

What is the issue?

Trying to run qwen3-coder-next:latest on Windows with a NVIDIA RTX 5070Ti, getting this error

qwen3-coder:30b works fine

Relevant log output

ggml_cuda_compute_forward: PAD failed
CUDA error: an illegal memory access was encountered
  current device: 0, in function ggml_cuda_compute_forward at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:2882
  err

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.15.5-rc2

Originally created by @rskupnik on GitHub (Feb 4, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14068 Originally assigned to: @jmorganca on GitHub. ### What is the issue? Trying to run qwen3-coder-next:latest on Windows with a NVIDIA RTX 5070Ti, getting this error qwen3-coder:30b works fine ### Relevant log output ```shell ggml_cuda_compute_forward: PAD failed CUDA error: an illegal memory access was encountered current device: 0, in function ggml_cuda_compute_forward at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:2882 err ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.15.5-rc2
GiteaMirror added the bug label 2026-04-22 18:59:37 -05:00
GiteaMirror commented 2026-04-22 19:01:25 -05:00
Author
Owner
Copy Link

@whackur commented on GitHub (Feb 4, 2026):

Same as me.

Windows NVIDIA RTX5090

ggml_cuda_compute_forward: PAD failed
CUDA error: an illegal memory access was encountered
<!-- gh-comment-id:3848224750 --> @whackur commented on GitHub (Feb 4, 2026): Same as me. Windows NVIDIA RTX5090 ``` ggml_cuda_compute_forward: PAD failed CUDA error: an illegal memory access was encountered ```
GiteaMirror commented 2026-04-22 19:01:25 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Feb 5, 2026):

This should be fixed in the latest RC. Sorry about that!

<!-- gh-comment-id:3855152837 --> @jmorganca commented on GitHub (Feb 5, 2026): This should be fixed in the latest RC. Sorry about that!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#34950
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?